INDEX

Explanations

instances of code-related syntax, specifically related to functions and object properties

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

isÃŃ

-0.16

oyer

-0.15

combe

-0.15

ude

-0.15

bett

-0.15

misc

-0.15

ilage

-0.14

eriod

-0.14

ayah

-0.14

 hala

-0.14

POSITIVE LOGITS

erver

0.17

_guid

0.15

ILINE

0.14

 CONSTANTS

0.14

ibri

0.14

 Frid

0.14

OKIE

0.14

 they

0.13

_GUID

0.13

jn

0.13

Activations Density 0.024%

instances of code-related syntax, specifically related to functions and object properties

No Comments

No Known Activations